[Top] [All Lists]

Re: du vs. ls

To: xfs@xxxxxxxxxxx
Subject: Re: du vs. ls
From: pille <pille+xfs+mailinglist+sgi@xxxxxxxxxxxx>
Date: Fri, 04 Jan 2013 19:19:11 +0100
In-reply-to: <20130104161449.GA25093@xxxxxxx>
References: <50E6F6D4.5090407@xxxxxxxxxxxx> <20130104161449.GA25093@xxxxxxx>
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:16.0) Gecko/20121104 Thunderbird/16.0.1
hi mathias and ben,

thanks for your fast reply.

i've already played around with the allocsize option.
xfs_bmap shows continuous files, as expected.
i'm just worried, because these mismatches never showed before (while
the volume was less than 50% full) and we didn't changed the workload.
a quick comparsion shows overhead of about 1% for the whole volume, but
given the 28MB overhead for 100MB, i expect this to increase in the future.

On 01/04/2013 05:14 PM, Matthias Schniedermeyer wrote:
> This fixes itself over time.
> Either do enough IO that the cache of the copy gets reused or umount or 

i cannot understand that. does a already written file gets reorganized
due to high I/O, because we've got that periodically.


<Prev in Thread] Current Thread [Next in Thread>